© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40463
    Prev
    Next
    INDEX
    Explanations

    costs and benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ሱስ
    0.51
    蛩
    0.49
    érieur
    0.49
     طریقے
    0.48
     Roj
    0.48
    țiuni
    0.48
    藥
    0.48
    রাজের
    0.48
     injurious
    0.48
    ⏜
    0.48
    POSITIVE LOGITS
    h
    0.51
    2
    0.46
     H
    0.45
    m
    0.45
     d
    0.43
    mathbf
    0.43
    *
    0.42
    #
    0.42
    disk
    0.41
    t
    0.41
    Activations Density 0.000%

    No Known Activations